Data Allocation in Heterogeneous Disk Arrays

Abstract

We consider the allocation of Virtual Arrays (VAs) with different RAID levels in a Heterogeneous Disk Array (HDA). This is expected to provide significant cost savings by consolidating multiple disk arrays into one. Disk load balancing across disk arrays is a by-product of HDA. We provide an example of potential performance benefits expected from HDA. The number of Virtual Disks (VDs) required to materialize a VA is determined by upper bounds on VD bandwidth and space per physical disk drive. Only RAID1 and RAID5 are considered in this paper, but we develop the analysis for other RAID levels. A VA allocation is successful if disks sharing VAs with a failed disk are not overloaded in degraded mode. Single-pass data allocation methods for HDA are evaluated with a synthetic stream of allocation requests. Experimental results show that allocation methods minimizing the maximum disk bandwidth and capacity utilization or their variance across all disks yield the maximum number of allocated VAs. When the disk bandwidth is the bottleneck resource we utilize clustered RAID5 arrays to increase the number of allocated VAs.

Rebuild processing in RAID5 with emphasis on the supplementary parity augmentation method[37]

“…This study reports on the effect of the width of an array on rebuild time, since XOR hardware constitute a bottleneck (see Figure 6 in that paper). The Heterogeneous Disk Array (HDA) is a similar proposal which places Virtual Arrays (VAs) with different levels across a subset of the disks, but allows sharing disk space on individual disks [36]. Rebuild processing in this case can be carried out at the level of VAs and the rebuilding of VAs accessed by more critical applications can be prioritized.…”